© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35869
    Prev
    Next
    INDEX
    Explanations

    military service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oola
    -0.09
    é«ĺæīĭ
    -0.09
    åľ¨çİ°åľº
    -0.09
    æĮģæľī
    -0.09
    çŃ¹çłģ
    -0.09
    verse
    -0.09
    ursive
    -0.09
    èĺ©
    -0.09
    头èĦij
    -0.08
    绿åŁİ
    -0.08
    POSITIVE LOGITS
     اÙĦعسÙĥرÙĬØ©
    0.13
    åĨĽäºº
    0.13
    åĨĽäºĭ
    0.13
    åĨĽå®ĺ
    0.12
    åĽ½éĺ²
    0.12
    Military
    0.12
    è»į
    0.12
    åĨĽ
    0.12
     military
    0.11
    å°ĨåĨĽ
    0.11
    Activations Density 0.137%

    No Known Activations